aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/vshare.py
blob: ea39a9051ebf8531113f24a8f7fb96d13d080a40 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import compat_chr
from ..utils import decode_packed_codes


class VShareIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?vshare\.io/[dv]/(?P<id>[^/?#&]+)'
    _TESTS = [{
        'url': 'https://vshare.io/d/0f64ce6',
        'md5': '17b39f55b5497ae8b59f5fbce8e35886',
        'info_dict': {
            'id': '0f64ce6',
            'title': 'vl14062007715967',
            'ext': 'mp4',
        }
    }, {
        'url': 'https://vshare.io/v/0f64ce6/width-650/height-430/1',
        'only_matching': True,
    }]

    def _extract_packed(self, webpage):
        packed = self._search_regex(r'(eval\(function.+)', webpage, 'packed code')
        unpacked = decode_packed_codes(packed)
        digits = self._search_regex(r'\[((?:\d+,?)+)\]', unpacked, 'digits')
        digits = digits.split(',')
        digits = [int(digit) for digit in digits]
        key_digit = self._search_regex(r'fromCharCode\(.+?(\d+)\)}', unpacked, 'key digit')
        chars = [compat_chr(d - int(key_digit)) for d in digits]
        return ''.join(chars)

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(
            'https://vshare.io/v/%s/width-650/height-430/1' % video_id, video_id)

        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
        title = title.split(' - ')[0]

        unpacked = self._extract_packed(webpage)
        video_urls = re.findall(r'<source src="([^"]+)', unpacked)
        formats = [{'url': video_url} for video_url in video_urls]
        return {
            'id': video_id,
            'title': title,
            'formats': formats,
        }

    @staticmethod
    def _extract_urls(webpage):
        return re.findall(
            r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?vshare\.io/v/[^/?#&]+)',
            webpage)